mirror of https://github.com/explosion/spaCy.git
32 lines
896 B
Python
32 lines
896 B
Python
|
# coding: utf8
|
||
|
|
from __future__ import unicode_literals
|
||
|
|
|
||
|
|
from .stop_words import STOP_WORDS
|
||
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
||
|
|
from .punctuation import TOKENIZER_INFIXES
|
||
|
|
|
||
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
||
|
|
from ..norm_exceptions import BASE_NORMS
|
||
|
|
from ...language import Language
|
||
|
|
from ...attrs import LANG, NORM
|
||
|
|
from ...util import update_exc, add_lookups
|
||
|
|
|
||
|
|
|
||
|
|
class LigurianDefaults(Language.Defaults):
|
||
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
||
|
|
lex_attr_getters[LANG] = lambda text: "lij"
|
||
|
|
lex_attr_getters[NORM] = add_lookups(
|
||
|
|
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
|
||
|
|
)
|
||
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
||
|
|
stop_words = STOP_WORDS
|
||
|
|
infixes = TOKENIZER_INFIXES
|
||
|
|
|
||
|
|
|
||
|
|
class Ligurian(Language):
|
||
|
|
lang = "lij"
|
||
|
|
Defaults = LigurianDefaults
|
||
|
|
|
||
|
|
|
||
|
|
__all__ = ["Ligurian"]
|